Great idea.
Voila: 
https://igraph.discourse.group/t/modularity-q-based-on-the-louvain-split-unexpected-values/159

Makis

On 29 Mar 2020, at 15:14, Szabolcs Horvát 
<[email protected]<mailto:[email protected]>> wrote:

I would recommend posting the question on https://igraph.discourse.group/ as 
that forum is meant to replace this mailing list, and provides a nicer 
discussion environment.

On Sun, 29 Mar 2020 at 15:08, serafim loukas 
<[email protected]<mailto:[email protected]>> wrote:
Just to add that I just found the python version of BCT (the Matlab toolbox 
that I used to benchmark igraph).

Using this: 
https://github.com/aestrivex/bctpy/blob/f9526a693a9af57051762442d8490dcdf2ebf4e3/bct/algorithms/modularity.py#L71,
 again I get approx. 0.1466 that matches the Matlab based results but is far 
from the python output (Q).

Makis

On 29 Mar 2020, at 14:56, serafim loukas 
<[email protected]<mailto:[email protected]>> wrote:

Hi igraph community,


I have a graph and I want to estimate the modularity (Q) based on the Louvain 
split of the graph.

In python I used igraph and to compare, I also estimated Q in Matlab.
Based on igraph, the Q is negative (weird) whereas the Q based on the Matlab 
estimation is possitive.

I would expect differences in the values but not by so far (+ shows modularity, 
- shows anti-modularity).
Any idea why this happens?

Makis

———————————

My code and data:


PYTHON

```
import numpy as np
import scipy.io<http://scipy.io/>
from igraph import *

A = scipy.io.loadmat('A.mat')['A']

graph = Graph.Weighted_Adjacency(A.tolist(), mode=ADJ_UNDIRECTED, 
attr="weight", loops=False)
Louvain = 
graph.community_multilevel(weights=graph.es<http://graph.es/>['weight'], 
return_levels=False)
Q = graph.modularity(Louvain)
print(Q)

-0.001847596203445795
```


MATLAB (https://sites.google.com/site/bctnet/measures/list)
using community_louvain.m: Louvain community detection algorithm

```
clear all
load('A.mat')
[M,Q]=community_louvain(A);

Q =

   0.1466
```

<A.mat>_______________________________________________
igraph-help mailing list
[email protected]<mailto:[email protected]>
https://lists.nongnu.org/mailman/listinfo/igraph-help

_______________________________________________
igraph-help mailing list
[email protected]<mailto:[email protected]>
https://lists.nongnu.org/mailman/listinfo/igraph-help
_______________________________________________
igraph-help mailing list
[email protected]<mailto:[email protected]>
https://lists.nongnu.org/mailman/listinfo/igraph-help

_______________________________________________
igraph-help mailing list
[email protected]
https://lists.nongnu.org/mailman/listinfo/igraph-help

Reply via email to